Downloads · 30 days
3
1% of all-time downloads
hushem_40x_deit_base_rms_0001_fold1
hkivancoral/hushem_40x_deit_base_rms_0001_fold1
hushem_40x_deit_base_rms_0001_fold1 is a image classification model from hkivancoral. Use it when you need a label for an image. It is set up for transformers. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
209
Public
Repo size
9.3 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin343 MB · 100%
At a glance
- Task
- Image Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- vit
- Access
- Public
- Created
- Dec 24, 2023
- Updated
- Dec 24, 2023
- SHA
- 0d29a412
Base models
Datasets
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
hushem_40x_deit_base_rms_0001_fold1
This model is a fine-tuned version of facebook/deit-base-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 2.4716
- Accuracy: 0.8222
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0001
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 50
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.0732 | 1.0 | 215 | 0.6365 | 0.7556 |
| 0.102 | 2.0 | 430 | 1.5996 | 0.6889 |
| 0.0272 | 3.0 | 645 | 0.8191 | 0.8 |
| 0.0001 | 4.0 | 860 | 0.8601 | 0.8 |
| 0.1057 | 5.0 | 1075 | 0.9797 | 0.7778 |
| 0.0863 | 6.0 | 1290 | 1.8140 | 0.6889 |
| 0.0131 | 7.0 | 1505 | 1.1217 | 0.8 |
| 0.0 | 8.0 | 1720 | 1.2704 | 0.8 |
| 0.0 | 9.0 | 1935 | 1.3271 | 0.8222 |
| 0.0 | 10.0 | 2150 | 1.4318 | 0.8222 |
| 0.0 | 11.0 | 2365 | 1.5412 | 0.7778 |
| 0.0 | 12.0 | 2580 | 1.6553 | 0.8 |
| 0.0 | 13.0 | 2795 | 1.7666 | 0.8 |
| 0.0 | 14.0 | 3010 | 1.8788 | 0.8444 |
| 0.0 | 15.0 | 3225 | 1.9590 | 0.8444 |
| 0.0 | 16.0 | 3440 | 2.0334 | 0.8444 |
| 0.0 | 17.0 | 3655 | 2.0934 | 0.8444 |
| 0.0 | 18.0 | 3870 | 2.1509 | 0.8444 |
| 0.0 | 19.0 | 4085 | 2.2044 | 0.8444 |
| 0.0 | 20.0 | 4300 | 2.2497 | 0.8444 |
| 0.0 | 21.0 | 4515 | 2.2856 | 0.8444 |
| 0.0 | 22.0 | 4730 | 2.3133 | 0.8444 |
| 0.0 | 23.0 | 4945 | 2.3351 | 0.8444 |
| 0.0 | 24.0 | 5160 | 2.3530 | 0.8444 |
| 0.0 | 25.0 | 5375 | 2.3678 | 0.8444 |
| 0.0 | 26.0 | 5590 | 2.3804 | 0.8444 |
| 0.0 | 27.0 | 5805 | 2.3914 | 0.8444 |
| 0.0 | 28.0 | 6020 | 2.4010 | 0.8222 |
| 0.0 | 29.0 | 6235 | 2.4094 | 0.8222 |
| 0.0 | 30.0 | 6450 | 2.4170 | 0.8222 |
| 0.0 | 31.0 | 6665 | 2.4237 | 0.8222 |
| 0.0 | 32.0 | 6880 | 2.4297 | 0.8222 |
| 0.0 | 33.0 | 7095 | 2.4351 | 0.8222 |
| 0.0 | 34.0 | 7310 | 2.4400 | 0.8222 |
| 0.0 | 35.0 | 7525 | 2.4444 | 0.8222 |
| 0.0 | 36.0 | 7740 | 2.4484 | 0.8222 |
| 0.0 | 37.0 | 7955 | 2.4519 | 0.8222 |
| 0.0 | 38.0 | 8170 | 2.4551 | 0.8222 |
| 0.0 | 39.0 | 8385 | 2.4580 | 0.8222 |
| 0.0 | 40.0 | 8600 | 2.4605 | 0.8222 |
| 0.0 | 41.0 | 8815 | 2.4628 | 0.8222 |
| 0.0 | 42.0 | 9030 | 2.4647 | 0.8222 |
| 0.0 | 43.0 | 9245 | 2.4664 | 0.8222 |
| 0.0 | 44.0 | 9460 | 2.4679 | 0.8222 |
| 0.0 | 45.0 | 9675 | 2.4691 | 0.8222 |
| 0.0 | 46.0 | 9890 | 2.4700 | 0.8222 |
| 0.0 | 47.0 | 10105 | 2.4708 | 0.8222 |
| 0.0 | 48.0 | 10320 | 2.4713 | 0.8222 |
| 0.0 | 49.0 | 10535 | 2.4716 | 0.8222 |
| 0.0 | 50.0 | 10750 | 2.4716 | 0.8222 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.1.0+cu121
- Datasets 2.12.0
- Tokenizers 0.13.2
- Task
- Image Classification
- Library
- transformers
- Type
- vit
- License
- apache-2.0
- Created
- Dec 24, 2023
- Updated
- Dec 24, 2023